Prediction of software fault-prone classes using an unsupervised hybrid SOM algorithm

Viji, C.; Rajkumar, .; Duraisamy, S.

doi:10.1007/s10586-018-1923-7

Cited by 10 publications

(4 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In fact, the prediction of the metrics related to software development process (e.g., number of bugs, time) is currently one of the needs of the product owners. Currently, we work on the time series based approach for such prediction, and we use models such as Holt-Winters, Exponential Smoothing and ARIMA as well as deep neural networks (Andrysiak et al 2014;Viji et al 2018).…”

Section: Discussionmentioning

confidence: 99%

Increasing product owners’ cognition and decision-making capabilities by data analysis approach

et al. 2018

View full text Add to dashboard Cite

In this paper, we focus on the innovative advanced data analysis dedicated for product owners in software development teams. The goal of our novel solutions is to increase cognition and decision making in rapid software development process. The major contribution of this work is the methodology and the tool that gathers the input raw data from the tools such as GitLab or SonarQube, and processes the data further (e.g., using Apache Kafka, Kibana, and Spark) to calculate and visualize more advanced metrics, product factors (e.g., in accordance to Quamoco model), and indicators, and to find correlations between them. Then, such high-level data are shown to product owners to increase their cognition, situational awareness, and decision-making capabilities. We have now implemented the proof-of-concept system which was positively validated by product owners using the real data from their projects.

show abstract

Section: Discussionmentioning

confidence: 99%

Increasing product owners’ cognition and decision-making capabilities by data analysis approach

et al. 2018

View full text Add to dashboard Cite

show abstract

“…Literature research shows that MLP can model highly nonlinear functions; IBk is a supervised machine learning algorithm, mainly used to solve classification and regression problems; Bagging has good stability and high prediction accuracy; RC is a machine learning classification algorithm composed of multiple classifiers, and multiple classifiers are based on meta-learning; GP is about the uncertainty of model prediction (confidence interval) and directly outputs the probability distribution of prediction points. SOM is an optimization algorithm for quadratic programming, while RT is an algorithm that reduces variance and greatly improves the performance of the model [4] . According to the demand of the multi-objective regression problem in this paper, the above seven model algorithms are selected to predict 10 kinds of isothermal transformation indexes respectively, and a CML model for predicting steel TTT diagram is formed according to the evaluation criteria.…”

Section: Modeling Strategymentioning

confidence: 99%

Research on TTT Curve of Alloy structural Steel based on Machine Learning

Gao

Fan²,

Xia³

et al. 2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

Austenite isothermal transformation curve (IT) of steel, also known as time-temperature-transformation curve (TTT) is an very important basic data for the heat treatment process design of steel. Traditionally, obtaining TTT information on metal mainly depends on experiments, so there are problems such as data dispersion, large errors, and inconvenient access in use. Using artificial intelligence and machine learning technology, the TTT curve of steel can be predicted with limited experimental data. Taking the authoritative data collected as training samples, the TTT curve of alloy structural steel was predicted based on a variety of machine learning algorithms.. Alloying element category, austenitizing temperature, phase transformation time are taken as input characteristics, and 10 kinds of transformation characteristics are taken as output targets. Correlation coefficient (R), and error analysis (RMSE, MAE) are used to evaluate and finalize the model, and the best algorithm is selected to form a combined-machine-learning algorithm (CML), and predict the TTT curve. Take the application of CML multi-model prediction method in 40Cr, 38CrMoAl, 35SiMn, and 20Mn2, and the predicted results reflect that the CML model has high prediction ability and good generalization.

show abstract

“…By Increases the defective software modules within the development and maintained costs for customer dissatisfaction. Controlling software quality and reducing development costs is a significant tool 12,13 . In the field of software, more and more consideration received by the software testing.…”

Section: Introductionmentioning

confidence: 99%

“…Controlling software quality and reducing development costs is a significant tool. 12,13 In the field of software, more and more consideration received by the software testing. The main aim of software testing is software quality improvement with the help of classifying as well as removing faults in the software development.…”

mentioning

confidence: 99%

Improved mayfly optimization deep stacked sparse auto encoder feature selection scorched gradient descent driven dropout XLM learning framework for software defect prediction

Anbu

2022

Concurrency and Computation

View full text Add to dashboard Cite

Summary Software testing is the process of improving software quality by classifying and removing defects in the software development. Previously, several methods were used for software defect prediction, but any one method did not provide sufficient accuracy. To overcome this issue, an improved may fly optimization with deep stacked sparse auto encoder feature selection scorched gradient descent driven dropout extreme learning machine framework (SDP‐IMFOFS‐GDDDXLMC) is proposed in this article for software defect prediction. Here, an IMFO method is considered for feature selection techniques. In feature selection technique, features are selected, such as PC1, PC4, and MC1 for selecting the probable minimal attribute. Then, GDDDXLMC approach is used to classify buggy and clean software detection. The proposed approach is implemented in MATLAB platform. The performance metrics, such as accuracy, precision, F‐measure, sensitivity, specificity, Mathew correlation coefficient (MCC) is examined to examine the performance of the proposed method. The simulation performance of the proposed SDP‐IMFOFS‐GDDDXLMC method attains higher accuracy 99.75%, 97.85%, 95.13%, 14.89%, 16.34%, 17.89%, and 98.79, higher sensitivity 96.34%, 91.23%, 89.12%, 12.67%, 17.56%, 18.90%, and 87.25% higher specificity 14.89%, 16.89%, 20.67%, 93.67%, 92.37%, 98.47%, and 94.78% compared with the existing methods, like SDP‐MLP‐PSO, SDP‐BPNN‐RBFNN, SDP‐CNN‐RNN‐LSTM, SDP‐KBN‐LIME, SDP‐SLDeep‐LSTM, SDP‐K‐PCA‐ELM, and SDP‐CNN‐PHI forest, respectively.

show abstract

Prediction of software fault-prone classes using an unsupervised hybrid SOM algorithm

Cited by 10 publications

References 14 publications

Increasing product owners’ cognition and decision-making capabilities by data analysis approach

Increasing product owners’ cognition and decision-making capabilities by data analysis approach

Research on TTT Curve of Alloy structural Steel based on Machine Learning

Improved mayfly optimization deep stacked sparse auto encoder feature selection scorched gradient descent driven dropout XLM learning framework for software defect prediction

Contact Info

Product

Resources

About